Methods and devices for labeling and/or matching

Abstract

Devices, such as computer readable media, and methods, such as automated methods, for labeling and / or matching. Some of the devices and methods are particularly useful for anatomical labeling of human airway trees. Some of the devices and methods are particularly useful for matching branch-points of human airway trees from represented in two or more graphs.

Description

CROSS-REFERENCE(S) TO RELATED APPLICATION(S) [0001] This application claims priority to U.S. Provisional Patent Application Ser. No. 60 / 568,184, filed May 5, 2004, the entire contents of which (including the appendices) are expressly incorporated by reference.STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH [0002] The government may own rights in this invention pursuant to National Institute of Health grant number HL-064368.BACKGROUND [0003] 1. Field of the Present Methods and Devices [0004] The present methods and devices relate generally to the fields of labeling and matching. More particular, they relate to labeling graphical representations of trees, such as automated anatomical labeling of human airway trees. They also relate to matching corresponding points of at least two graphical representations, such as automated matching of corresponding branch-points of at least two graphical representations of a tree, such as a human airway tree. [0005] 2. Description of Related Art [00...

AI Technical Summary

Problems solved by technology

Lung diseases like lung cancer, emphysema, and cystic fibrosis are a significant cause of disability and premature death in western countries.

The manual analysis of these images is often time-consuming, tedious, and error prone.

And with the high volume of scans taken, manual analysis is in many cases not economical.

Functional understanding of pulmonary anatomy as well as the natural course of respiratory diseases like asthma, emphysema, cystic fibrosis, and many others is limited by our inability to repeatedly evaluate the same region of the lungs time after time and perform accurate and reliable positionally corresponding measurements.

Branch-point matching and anatomical labeling are both tedious and error-prone to perform manually.

Working with human in-vivo data poses challenges.

Pisupati et al. stated that they expect the method to fail on human in-vivo scans.

(1999)), but his method was applied only to phantom data and does not tolerate false branches.

Additionally, the algorithm is sensitive to missing and added (false) branches.

The method cannot automatically handle false branches—they have to be pruned manually in a preprocessing step.

Images